Structural Health Monitoring of Composite Structures via Machine Learning of Mechanoluminescence

The goal of this paper is to develop a machine learning algorithm for structural health monitoring of polymer composites with mechanoluminescent phosphors as distributed sensors. Mechanoluminescence is the phenomenon of light emission from organic/inorganic materials due to mechanical stimuli. Distributed sensors collect a large amount of data and contain structural response information that is difficult to analyze using classical or continuum models. Hence, approaches to analyze this data using machine learning or deep learning is necessary to develop models that describe initiation of damage, propagation and ultimately structural failure. This paper focuses on developing a machine learning algorithm that predicts the elastic modulus of a structure as a function of input parameters such as stress and measured light output. The training data for the algorithm utilizes experimental results from cyclical loading of elastomeric composite coupons impregnated with ML particles. A multivariate linear regression is performed on the elastic modulus within the training data as a function of stress and ML emission intensity. Error in predicted elastic modulus is minimized using a gradient descent algorithm. The machine learning algorithm outlined in this paper is expected to provide insights into structural response and deterioration of mechanical properties in real-time that cannot be obtained using a finite array of sensors.